© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    line drawings

    np_acts-logits-general · gemini-2.5-flash-lite

    geometric shapes and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     serviços
    0.43
     প্রশাসন
    0.41
     privés
    0.41
    <unused1>
    0.40
    esség
    0.40
     گور
    0.40
     mieście
    0.40
    🚛
    0.39
    บาล
    0.39
    acariy
    0.38
    POSITIVE LOGITS
     arrows
    0.87
     arrow
    0.77
     lines
    0.69
     dashed
    0.67
     dotted
    0.67
     dots
    0.66
     line
    0.64
     vertical
    0.64
     horizontal
    0.64
     circles
    0.64
    Activations Density 0.084%

    No Known Activations